@inproceedings{celebi-ozgur-2014-self,
title = "Self-training a Constituency Parser using n-gram Trees",
author = {{\c{C}}elebi, Arda and
{\"O}zg{\"u}r, Arzucan},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/543_Paper.pdf",
pages = "2893--2896",
abstract = "In this study, we tackle the problem of self-training a feature-rich discriminative constituency parser. We approach the self-training problem with the assumption that while the full sentence parse tree produced by a parser may contain errors, some portions of it are more likely to be correct. We hypothesize that instead of feeding the parser the guessed full sentence parse trees of its own, we can break them down into smaller ones, namely n-gram trees, and perform self-training on them. We build an n-gram parser and transfer the distinct expertise of the $n$-gram parser to the full sentence parser by using the Hierarchical Joint Learning (HJL) approach. The resulting jointly self-trained parser obtains slight improvement over the baseline.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="celebi-ozgur-2014-self">
<titleInfo>
<title>Self-training a Constituency Parser using n-gram Trees</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arda</namePart>
<namePart type="family">Çelebi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arzucan</namePart>
<namePart type="family">Özgür</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hrafn</namePart>
<namePart type="family">Loftsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this study, we tackle the problem of self-training a feature-rich discriminative constituency parser. We approach the self-training problem with the assumption that while the full sentence parse tree produced by a parser may contain errors, some portions of it are more likely to be correct. We hypothesize that instead of feeding the parser the guessed full sentence parse trees of its own, we can break them down into smaller ones, namely n-gram trees, and perform self-training on them. We build an n-gram parser and transfer the distinct expertise of the n-gram parser to the full sentence parser by using the Hierarchical Joint Learning (HJL) approach. The resulting jointly self-trained parser obtains slight improvement over the baseline.</abstract>
<identifier type="citekey">celebi-ozgur-2014-self</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/543_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2893</start>
<end>2896</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-training a Constituency Parser using n-gram Trees
%A Çelebi, Arda
%A Özgür, Arzucan
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F celebi-ozgur-2014-self
%X In this study, we tackle the problem of self-training a feature-rich discriminative constituency parser. We approach the self-training problem with the assumption that while the full sentence parse tree produced by a parser may contain errors, some portions of it are more likely to be correct. We hypothesize that instead of feeding the parser the guessed full sentence parse trees of its own, we can break them down into smaller ones, namely n-gram trees, and perform self-training on them. We build an n-gram parser and transfer the distinct expertise of the n-gram parser to the full sentence parser by using the Hierarchical Joint Learning (HJL) approach. The resulting jointly self-trained parser obtains slight improvement over the baseline.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/543_Paper.pdf
%P 2893-2896
Markdown (Informal)
[Self-training a Constituency Parser using n-gram Trees](http://www.lrec-conf.org/proceedings/lrec2014/pdf/543_Paper.pdf) (Çelebi & Özgür, LREC 2014)
ACL
- Arda Çelebi and Arzucan Özgür. 2014. Self-training a Constituency Parser using n-gram Trees. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2893–2896, Reykjavik, Iceland. European Language Resources Association (ELRA).